How to Use the CircleCI MCP in OpenAI Agents SDK

Q: How does CircleCI workflow monitoring work with OpenAI Agents SDK handoffs?

A triage agent can call listpipelineworkflows to find active runs. If a workflow fails, the agent passes the workflow ID to a specialist agent that runs listworkflowjobs to find the exact broken step.

Trigger CircleCI pipelines and inspect failed jobs directly from your OpenAI Agents SDK workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CircleCI MCP to OpenAI Agents SDK

Create your Vinkius account to connect CircleCI to OpenAI Agents SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup CircleCI with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger pipelines with OpenAI Agents SDK guardrails

This MCP Server exposes the `trigger_cci_pipeline` tool so your OpenAI agents can kick off builds when code changes or deployments are requested. You can wire this directly into your agent definition to let your system run integration tests autonomously. Because you are using the OpenAI Agents SDK, you can set up strict validation guardrails before the agent calls `trigger_cci_pipeline`. This prevents accidental triggers of expensive build pipelines if the agent misinterprets a user's prompt.

Inspect failing runs using built-in agent handoffs

When a build fails, your main agent can hand off the task to a specialized debugging agent that uses `list_pipeline_workflows` and `list_workflow_jobs` to isolate the error. The second agent inspects the exact step that broke without cluttering your primary prompt context. Once the failing job is identified, the agent calls `get_job_details` to pull the failure logs. You can trace this entire multi-agent handoff inside your OpenAI dashboard to see exactly how the agents collaborated to diagnose the broken CircleCI build.

List shared contexts safely during agent execution

Your agents can query `list_cci_contexts` to verify that the correct environment variables and secrets are available for a given organization before running a job. This stops builds from failing halfway through due to missing credentials. The OpenAI Agents SDK registers these tools automatically using our hosted MCP Server endpoint. Your agent gets instant access to the context lists without you writing custom API wrapper code.

Setup guide

Set up CircleCI MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all CircleCI tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives CircleCI tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate CircleCI tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="CircleCI Agent",
            instructions="You have access to CircleCI tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by CircleCI. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect CircleCI now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about CircleCI MCP in OpenAI Agents SDK

Use the MCPServerStreamableHttp client to connect to the Vinkius endpoint, then pass the server to your agent's mcp_servers list. Your agent will automatically find and use the trigger_cci_pipeline tool when a build is requested.

Yes. You can restrict the tools exposed by the MCP Server during initialization or handle it within the agent's system instructions. This keeps the agent focused on safe actions like get_workflow_details instead of triggering new builds.

A triage agent can call list_pipeline_workflows to find active runs. If a workflow fails, the agent passes the workflow ID to a specialist agent that runs list_workflow_jobs to find the exact broken step.

Setting this option prevents the SDK from querying the Vinkius endpoint for tool definitions on every single turn. It speeds up agent response times when calling tools like get_my_cci_profile or list_cci_pipelines.

Vinkius runs the server in an isolated, ephemeral V8 sandbox. Your CircleCI API tokens are injected securely at runtime and never logged or stored on disk, protecting your pipeline credentials from exposure.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript